A reinforcement learning approach to the stochastic cutting stock problem.
Anselmo Ramalho Pitombeira NetoArthur H. Fonseca MurtaPublished in: EURO J. Comput. Optim. (2022)
Keyphrases
- reinforcement learning
- direct policy search
- stochastic approximation
- learning automata
- function approximation
- integer programming
- monte carlo
- machine learning
- control policies
- markov decision processes
- control problems
- small sized
- model free
- stochastic optimization
- policy iteration
- reinforcement learning algorithms
- optimal policy
- state space
- stochastic nature
- stochastic model
- robotic control
- model free reinforcement learning
- stochastic programming
- temporal difference
- column generation
- learning algorithm
- temporal difference learning
- state dependent
- continuous state spaces
- action selection
- supervised learning